In modern security, devices, individuals, and communications require unprecedentedly unique identifiers and cryptographic keys. One emerging method for guaranteeing digital security is to take advantage of a physical unclonable function (PUF). Paper PUF has been extensively demonstrated as a hidden security for a wide range of paper documents and packaging. However, the readout of the existing paper PUF is far less robust and has a smaller key storage capacity. Therefore, we propose using electrospinning as a universal technique to fabricate a strong, in-built and high-capacity PUF based on the random morphologies of electrospun nanofibers (ESNFs). To achieve a high key space within a given sensor, multicolor carbon dots are adopted to label individual fibers to create four independent challenge–response pairs: dark-field scattering, fluorescent red, green and blue emissions. Through a modified perceptional hashing, each ESNF-PUF sensor generates a 256-bit fingerprint per challenge–response pair. A bitstream of 300 Kbits from 48 PUF sensors passes all of thirteen NIST randomness tests without any post-processing. The entropy of the fingerprint is estimated to be 246 bits, resulting in a key space of 5²⁴⁶, simultaneously the false positive rate is below 10⁻⁹, and more than 102.4 Mbit cm⁻² binary keys are generated from the ESNF-PUFs, providing an enormous address space for one-time pad applications. The conciseness of fingerprints has also been investigated, revealing a trade-off between the entropy and robustness of the PUF system. For practical application, the signature and authentication process of the secured paper document derived by electrospinning are demonstrated. In addition, the ESNF-PUF could be used as a chaotic system to encrypt and decrypt the data robustly.

Federated learning is a distributed machine learning approach designed to tackle the problems of data silos and the security of raw data. Nevertheless, it remains susceptible to privacy leakage risks and aggregation server tampering attacks. Current privacy-preserving methods often involve significant computational and communication overheads, which can be challenging in resource-limited settings, hindering their practical application. To overcome these obstacles, this article proposes an efficient secure aggregation scheme based on secret sharing-GVSA. GVSA safeguards the privacy of local models through a masking technique and improves the system’s resilience to user dropouts by utilizing secret sharing. Furthermore, GVSA implements a dual aggregation approach and incorporates lightweight validation tags to verify the accuracy of the aggregation results. By adopting a grouping strategy, GVSA effectively minimizes the computational burden on both users and the server, making it well-suited for resource-constrained environments. We compare GVSA with leading existing methods and assess its performance through various experimental setups. Experimental results demonstrate that GVSA maintains high security while effectively preserving model accuracy. Compared to FedAvg, GVSA incurs only approximately 7% additional computational overhead. Furthermore, compared to other secure aggregation schemes with the same security level, GVSA achieves approximately a 2.3\(\times\) improvement in training speed.

Unmanned Aerial Vehicle (UAV) swarms not only expanded the application areas of UAVs but also brought more complex challenges to security. Both the data collected by UAVs and UAVs themselves are easy targets for hackers. Once a hacker has intercepted communication information or hijacked a UAV, it can cause the disclosure of information and even affect the normal flight of the UAV. In terms of authentication, existing research focuses on building peer-to-peer networks through devices that support blockchain deployments at the edge nodes to form blockchain networks. UAVs cannot run blockchains directly, so fog nodes need to be introduced to assist UAVs in achieving authentication. This paper proposes a UAV authentication solution based on the fog node-assisted blockchain. The solution incorporates smart contracts to ensure trust, along with on-chain registration and authentication for UAVs. In the design of this paper, the main use is made of fog nodes at the edge of each block. The fog nodes serve as agents to register and authenticate the UAVs in their area on the blockchain, thus enabling the authentication of UAVs in different fog node areas. In this paper, the analysis of gas consumption yields a total economic benefit cost of about $$\yen $$¥ 12.77, which is negligible for the safety of the UAVs. Meanwhile, the paper compares the computational overheads, and within 10 UAVs, the computational overhead of this scheme is less than 50 ms, which is significantly lower than the other two schemes.

In response to the rapid growth of credit-investigation data, data redundancy among credit-investigation agencies, privacy leakages of credit-investigation data subjects, and data security risks have been reported. This study proposes a privacy-protection scheme for a credit-investigation system based on blockchain technology, which realizes the secure sharing of credit-investigation data among multiple entities such as credit-investigation users, credit-investigation agencies, and cloud service providers. This scheme is based on blockchain technology to solve the problem of islanding of credit-investigation data and is based on zero-knowledge-proof technology, which works by submitting a proof to the smart contract to achieve anonymous identity authentication, ensuring that the identity privacy of credit-investigation users is not disclosed; this scheme is also based on searchable-symmetric-encryption technology to realize the retrieval of the ciphertext of the credit-investigation data. A security analysis showed that this scheme guarantees the confidentiality, the availability, the tamper-proofability, and the ciphertext searchability of credit-investigation data, as well as the fairness and anonymity of identity authentication in the credit-investigation data query. An efficiency analysis showed that, compared with similar identity-authentication schemes, the proof key of this scheme is smaller, and the verification time is shorter. Compared with similar ciphertext-retrieval schemes, the time for this scheme to generate indexes and trapdoors and return search results is significantly shorter.

In recommender systems, user reviews on items contain rich semantic information, which can express users’ preferences and item features. However, existing review-based recommendation methods either use the static word vector model or cannot effectively extract long sequence features in reviews, resulting in the limited ability of user feature expression. Furthermore, the impact of different or useless feature interactions between users and items on recommendation performance is ignored. Therefore, we propose an attentional factorization machine with review-based user–item interaction for recommendation (AFMRUI), which first leverages RoBERTa to obtain the embedding feature of each user/item review, and combines bidirectional gated recurrent units with attention network to highlight more useful information in both user and item reviews. Then we adopt AFM to learn user–item feature interactions to distinguish the importance of different user–item feature interactions and further to obtain more accurate rating prediction, so as to promote recommendation. Finally, we conducted performance evaluation on five real-world datasets. Experimental results on five datasets demonstrated that the proposed AFMRUI outperformed the state-of-the-art review-based methods regarding two commonly used evaluation metrics.